A Novel Hybrid Segmentation Approach for Decision Support: A Case Study in Banking.

The article focuses on enhancing decision-making in customer-centric organizations by improving the traditional RFM (Recency, Frequency, Monetary) scoring model through the introduction of a new parameter called Adoption, forming the RFMA model. This dynamic model integrates weighted RFM values across multiple channels and applies K-means clustering to segment customers based on their behavior, demonstrated via a case study involving a major private bank aiming to increase digital channel usage. The RFMA model successfully categorized customers into four distinct clusters reflecting varying levels of digital adoption and transactional behavior, enabling stakeholders to tailor strategies accordingly. Evaluations showed the model to be stable, robust, and effective in supporting business objectives, with potential applicability across various industries and opportunities for further refinement in scoring and segmentation techniques.